{"id":"https://openalex.org/W4375869384","doi":"https://doi.org/10.1109/icassp49357.2023.10094949","title":"GOP-Based Latent Refinement for Learned Video Coding","display_name":"GOP-Based Latent Refinement for Learned Video Coding","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869384","doi":"https://doi.org/10.1109/icassp49357.2023.10094949"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04383515v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075452655","display_name":"Mohsen Abdoli","orcid":"https://orcid.org/0000-0002-9308-4156"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohsen Abdoli","raw_affiliation_strings":["IRT B-Com,Cesson-Sévigné,France,35510"],"affiliations":[{"raw_affiliation_string":"IRT B-Com,Cesson-Sévigné,France,35510","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025851887","display_name":"Gordon Clare","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gordon Clare","raw_affiliation_strings":["IRT B-Com,Cesson-Sévigné,France,35510"],"affiliations":[{"raw_affiliation_string":"IRT B-Com,Cesson-Sévigné,France,35510","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027444024","display_name":"F\u00e9lix Henry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F\u00e9lix Henry","raw_affiliation_strings":["IRT B-Com,Cesson-Sévigné,France,35510"],"affiliations":[{"raw_affiliation_string":"IRT B-Com,Cesson-Sévigné,France,35510","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075452655"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8053,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70178372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7397139072418213},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.737360954284668},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6331617832183838},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.522800087928772},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4616244435310364},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4416219890117645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43718913197517395},{"id":"https://openalex.org/keywords/group-of-pictures","display_name":"Group of pictures","score":0.41988256573677063},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.4112704396247864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3559454083442688},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.306282639503479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15911033749580383},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11614939570426941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08258005976676941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7397139072418213},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.737360954284668},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6331617832183838},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.522800087928772},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4616244435310364},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4416219890117645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43718913197517395},{"id":"https://openalex.org/C196496179","wikidata":"https://www.wikidata.org/wiki/Q860741","display_name":"Group of pictures","level":3,"score":0.41988256573677063},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.4112704396247864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3559454083442688},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.306282639503479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15911033749580383},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11614939570426941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08258005976676941},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04383515v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04383515","pdf_url":"https://hal.science/hal-04383515v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10094949⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04383515v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04383515","pdf_url":"https://hal.science/hal-04383515v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10094949⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869384.pdf","grobid_xml":"https://content.openalex.org/works/W4375869384.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2552465432","https://openalex.org/W2747329762","https://openalex.org/W2969260367","https://openalex.org/W2992051623","https://openalex.org/W3033326602","https://openalex.org/W3110286842","https://openalex.org/W3169876831","https://openalex.org/W3174364798","https://openalex.org/W3175941296","https://openalex.org/W3194998642","https://openalex.org/W3216456501","https://openalex.org/W4224925593","https://openalex.org/W4226168429","https://openalex.org/W4283821816","https://openalex.org/W4292827998","https://openalex.org/W4317555479","https://openalex.org/W6763486759","https://openalex.org/W6839504577"],"related_works":["https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W2107680156","https://openalex.org/W4301184752","https://openalex.org/W2288771647","https://openalex.org/W2751422192","https://openalex.org/W1509797384","https://openalex.org/W1201576901"],"abstract_inverted_index":{"This":[0,44,70],"paper":[1],"presents":[2],"a":[3,29,49,57,66,107,174],"method":[4,150],"allowing":[5],"learned":[6],"video":[7,42],"encoders":[8],"to":[9,15,76,121],"apply":[10],"arbitrary":[11],"latent":[12,30,38,103,130,147],"refinement":[13],"strategies":[14],"serve":[16],"as":[17,48,80],"RateDistortion":[18],"Optimization":[19],"(RDO)":[20],"at":[21],"the":[22,41,78,81,88,102,113,125,136,145],"time":[23],"of":[24,40,51,54,62,95,116,128,138,159],"encoding.":[25],"To":[26],"do":[27],"so,":[28],"domain":[31],"search":[32,45],"is":[33,46,73,110],"applied":[34,171],"on":[35,132,172],"an":[36],"initial":[37],"representation":[39,104],"signal.":[43],"implemented":[47],"set":[50],"iterations,":[52],"each":[53,99],"which":[55],"performs":[56],"gradient":[58],"descent":[59],"with":[60],"back-propagation":[61],"error":[63],"defined":[64],"by":[65,153],"Lagrangian":[67],"RD":[68],"cost.":[69],"cost":[71,82,114],"function":[72,83,115],"intentionally":[74],"chosen":[75],"be":[77],"same":[79],"that":[84,93,144],"was":[85],"used":[86],"during":[87],"end-to-end":[89,177],"model":[90,97],"training,":[91],"except":[92],"instead":[94],"updating":[96],"weights,":[98],"iteration":[100],"fine-tunes":[101],"itself.":[105],"Moreover,":[106],"temporal":[108],"look-ahead":[109],"integrated":[111],"in":[112,135,157,163],"I":[117],"and":[118,155,166],"P":[119],"frames":[120,134],"take":[122],"into":[123],"account":[124],"cascade":[126],"effect":[127],"their":[129],"fine-tuning":[131],"subsequent":[133],"Group":[137],"Pictures":[139],"(GOP).":[140],"The":[141],"experiments":[142],"show":[143],"proposed":[146],"space":[148],"RDO":[149],"can":[151],"improve":[152],"11.6%":[154],"9.4%":[156],"terms":[158],"BD-BR":[160],"coding":[161],"efficiency":[162],"Random-Access":[164],"(RA)":[165],"All-Intra":[167],"(AI)":[168],"configurations,":[169],"when":[170],"top":[173],"high-performance":[175],"opensource":[176],"codec.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}